A New Finger Vein Recognition Method Based on LBP and 2DPCA

Abstract

Finger vein recognition is an emerging biometrics technology. Using the global information of finger vein images, this paper presents a method of finger vein recognition combining the texture feature fusion algorithm of LBP operator and 2DPCA algorithm. First of all, the texture feature of finger vein image was extracted by LBP operator, and then a two-dimensional principal component analysis is used to project the transformed image for feature extraction. Euclidean distance measures the similarity between test and training samples. Experiments in the Tianjin Intelligence Lab image database and FV-USM finger vein database show that the proposed method is effective and reliable and improves the performance of a finger-vein identification system.